PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Kernel Measures of Conditional Dependence
Kenji Fukumizu, Arthur Gretton, xiaohai sun and Bernhard Schölkopf
In: NIPS 2007, 03 Dec - 06 Dec 2007, Vancouver Canada.

Abstract

We propose a new measure of conditional dependence of random variables, based on normalized cross-covariance operators on reproducing kernel Hilbert spaces. Unlike previous kernel dependence measures, the proposed criterion does not depend on the choice of kernel in the limit of infinite data, for a wide class of kernels. At the same time, it has a straightforward empirical estimate with good convergence behaviour. We discuss the theoretical properties of the measure, and demonstrate its application in experiments.

EPrint Type:Conference or Workshop Item (Spotlight)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Theory & Algorithms
ID Code:3143
Deposited By:Arthur Gretton
Deposited On:21 December 2007